Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4998 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1501. Min Range: -4.1501

Max Act: 4.1501. Min Act: -0.0000

Data Index: 629395 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 4.1501. Min Range: -4.1501

Max Act: 3.2451. Min Act: -0.0000

Data Index: 813464 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.9038. Min Act: -0.0000

Data Index: 1219822 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.7613. Min Act: -0.0000

Data Index: 458321 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 4.1501. Min Range: -4.1501

Max Act: 3.0391. Min Act: -0.0000

Data Index: 86585 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.9738. Min Act: -0.0000

Data Index: 1271822 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.4475. Min Act: -0.0000

Data Index: 60192 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.6695. Min Act: -0.0000

Data Index: 1146452 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.6239. Min Act: -0.0000

Data Index: 715927 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.4875. Min Act: -0.0000

Data Index: 47600 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.4614. Min Act: -0.0000

Data Index: 256951 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.3447. Min Act: -0.0000

Data Index: 262514 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.3307. Min Act: -0.0000

Data Index: 1300568 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.4509. Min Act: -0.0000

Data Index: 775366 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.6009. Min Act: -0.0000

Data Index: 1348403 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.3249. Min Act: -0.0000

Data Index: 586564 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.2944. Min Act: -0.0000

Data Index: 102473 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.4191. Min Act: -0.0000

Data Index: 1184225 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.2605. Min Act: -0.0000

Data Index: 580281 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 4.1501. Min Range: -4.1501

Max Act: 2.2623. Min Act: -0.0000

Data Index: 533865 (C4 (Web Text))

Max Activating Token Index: 1023